Batch-level Experience Replay with Review for Continual Learning

July 11, 2020 · Entered Twilight · 🏛 arXiv.org

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, CVPR2020_CLVision_challenge.pdf, Dockerfile, LICENSE, README.md, build_docker_image.sh, check_submission.sh, config, core50, create_submission.sh, create_submission_in_docker.sh, environment.yml, fetch_data_and_setup.sh, final_submission.py, general_main.py, logo, models, utils

Authors Zheda Mai, Hyunwoo Kim, Jihwan Jeong, Scott Sanner arXiv ID 2007.05683 Category cs.LG: Machine Learning Cross-listed cs.AI, cs.CV, stat.ML Citations 18 Venue arXiv.org Repository https://github.com/RaptorMai/CVPR20_CLVision_challenge ⭐ 46 Last Checked 1 month ago

Abstract

Continual learning is a branch of deep learning that seeks to strike a balance between learning stability and plasticity. The CVPR 2020 CLVision Continual Learning for Computer Vision challenge is dedicated to evaluating and advancing the current state-of-the-art continual learning methods using the CORe50 dataset with three different continual learning scenarios. This paper presents our approach, called Batch-level Experience Replay with Review, to this challenge. Our team achieved the 1'st place in all three scenarios out of 79 participated teams. The codebase of our implementation is publicly available at https://github.com/RaptorMai/CVPR20_CLVision_challenge